INDEX

Explanations

phrases related to achievements or accomplishments

oai_token-act-pair · gpt-3.5-turbo

terms related to achievements or accomplishments

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 slic

-0.77

olid

-0.74

oval

-0.72

pher

-0.71

cos

-0.70

folk

-0.68

law

-0.68

ned

-0.66

trop

-0.65

eric

-0.65

POSITIVE LOGITS

 Achievement

1.11

 achievement

1.11

 attainment

1.07

 achie

1.04

 accomplishment

0.92

 achievements

0.83

ment

0.83

rious

0.81

chieve

0.80

 Achievements

0.76

Activations Density 0.040%

phrases related to achievements or accomplishments

terms related to achievements or accomplishments

No Comments

No Known Activations